Instructions to use Renesas/Qwen2.5-VL-3B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Renesas/Qwen2.5-VL-3B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Renesas/Qwen2.5-VL-3B-Instruct-GGUF",
	filename="fp16/Qwen2.5-VL-3B-Instruct-fp16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Renesas/Qwen2.5-VL-3B-Instruct-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Renesas/Qwen2.5-VL-3B-Instruct-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf Renesas/Qwen2.5-VL-3B-Instruct-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Renesas/Qwen2.5-VL-3B-Instruct-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf Renesas/Qwen2.5-VL-3B-Instruct-GGUF:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Renesas/Qwen2.5-VL-3B-Instruct-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf Renesas/Qwen2.5-VL-3B-Instruct-GGUF:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Renesas/Qwen2.5-VL-3B-Instruct-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Renesas/Qwen2.5-VL-3B-Instruct-GGUF:F16

Use Docker

docker model run hf.co/Renesas/Qwen2.5-VL-3B-Instruct-GGUF:F16

LM Studio
Jan

vLLM

How to use Renesas/Qwen2.5-VL-3B-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Renesas/Qwen2.5-VL-3B-Instruct-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Renesas/Qwen2.5-VL-3B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Renesas/Qwen2.5-VL-3B-Instruct-GGUF:F16

Ollama
How to use Renesas/Qwen2.5-VL-3B-Instruct-GGUF with Ollama:
```
ollama run hf.co/Renesas/Qwen2.5-VL-3B-Instruct-GGUF:F16
```

Unsloth Studio

How to use Renesas/Qwen2.5-VL-3B-Instruct-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Renesas/Qwen2.5-VL-3B-Instruct-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Renesas/Qwen2.5-VL-3B-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Renesas/Qwen2.5-VL-3B-Instruct-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use Renesas/Qwen2.5-VL-3B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/Renesas/Qwen2.5-VL-3B-Instruct-GGUF:F16
```

Lemonade

How to use Renesas/Qwen2.5-VL-3B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Renesas/Qwen2.5-VL-3B-Instruct-GGUF:F16

Run and chat with the model

lemonade run user.Qwen2.5-VL-3B-Instruct-GGUF-F16

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Qwen2.5-VL-3B-Instruct - Renesas X5H

Introduction

This repository contains Qwen2.5-VL-3B-Instruct model, optimized for Renesas X5H platform for Image inference.

Model Architecture: Qwen2.5‑VL is an auto‑regressive vision‑language model built on a decoder‑only Transformer architecture, integrating a visual encoder with the language model through a multimodal projector, and incorporating optimized attention mechanisms and normalization strategies to improve training stability and inference efficiency.
Source Model: Qwen/Qwen2.5-VL-3B-Instruct

Performance

The following performance metrics were measured with a prompt.

Model	Precision	Device	Offloading	token generator (tokens/sec)
Qwen2.5-VL-3B-Instruct	W4A16	X5H - Single Cluster NPX	VisionTower NPX(fp16) + Language Decoder (w4a16)	14.09 tokens/sec
Qwen2.5-VL-3B-Instruct	FP16	X5H - Single Cluster NPX	VisionTower NPX(fp16) + Language Decoder (fp16)	8.21 tokens/sec

Prerequisites

To run model, you need:

Renesas X5H Board
Hugging Face CLI: For downloading the model.

Deployment

Qwen2.5-VL-3B-Instruct (W4A16)

Download the installer qwen2p5-vl-w4a16-runner-0.1.0-Linux.sh from Files and version tab.

Copy the installer to the X5H board and run the installer.

bash ./qwen2p5-vl-w4a16-runner-0.1.0-Linux.sh --prefix=./ --exclude-subdir --skip-license

Download the model files - Qwen2.5-VL-3B-Instruct-fp16.gguf and mmproj-Qwen2.5-VL-3B-Instruct-f16.gguf from Files and version tab and copy to the installed directory on the X5H board.

Expected directory structure on the X5H board.

 qwen2p5-vl-w4a16-runner/
 ├── firmwares
 ├── kernel_modules
 ├── mmproj-Qwen2.5-VL-3B-Instruct-f16.gguf
 ├── Qwen2.5-VL-3B-Instruct-fp16.gguf
 ├── qwen2p5-vl-w4a16-runner
 ├── qwen2p5-w4a16
 ├── scripts
 └── setup_npu.sh

Inference (W4A16)

bash ./setup_npu.sh

./qwen2p5-vl-w4a16-runner -m Qwen2.5-VL-3B-Instruct-fp16.gguf -v mmproj-Qwen2.5-VL-3B-Instruct-f16.gguf -i car-1.jpg -p "Describe this image"

Qwen2.5-VL-3B-Instruct (FP16)

Download the installer qwen2p5-vl-runner-0.1.0-Linux.sh from Files and version tab.

Copy the installer to the X5H board and run the installer.

bash ./qwen2p5-vl-runner-0.1.0-Linux.sh --prefix=./ --exclude-subdir --skip-license

Download the model files - Qwen2.5-VL-3B-Instruct-fp16.gguf and mmproj-Qwen2.5-VL-3B-Instruct-f16.gguf from Files and version tab and copy to the installed directory on the X5H board.

Expected directory structure on the X5H board.

 qwen2p5-vl-runner/
 ├── firmwares
 ├── kernel_modules
 ├── mmproj-Qwen2.5-VL-3B-Instruct-f16.gguf
 ├── Qwen2.5-VL-3B-Instruct-fp16.gguf
 ├── qwen2p5-vl-runner
 ├── scripts
 └── setup_npu.sh

Inference (FP16)

bash ./setup_npu.sh

./qwen2p5-vl-runner -m Qwen2.5-VL-3B-Instruct-fp16.gguf -v mmproj-Qwen2.5-VL-3B-Instruct-f16.gguf -i test_img/sport-car.jpg -p "Describe this image"

Downloads last month: 31

GGUF

Model size

3B params

Architecture

qwen2vl

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Collections including Renesas/Qwen2.5-VL-3B-Instruct-GGUF

GGUF

Collection

7 items • Updated 8 days ago

X5H Hardware - NPU

Collection

10 items • Updated 8 days ago